Unformatted text preview: error is given by half the length of a conﬁdence interval. Suppose we require the margin of error not to be
more than a number E at the (1 − α)% conﬁdence interval, we need a sample of size n such that
n ≥ zα
E Hypothesis testing for the population mean when variance is known
Assume the population follows Normal distribution with mean µ and variance σ 2 (known).
µ = µ0 or µ ≥ µ0
µ = µ0 or µ ≤ µ0 H1
µ < µ0
µ > µ0 Two-tailed µ = µ0 µ = µ0 Reject H0 if and only i...
View Full Document